project-context

A workflow for finding project-specific documentation before changing code. It uses a Context MCP server to identify relevant project knowledge and then reads only the needed documents.

In plain words
What is it for?
Use it when working in an unfamiliar project, locating its architecture or configuration guidance, or making changes that must follow existing documentation.
Why use it?
It reduces the risk of missing repository rules, architecture decisions, naming conventions, or instructions that are not obvious from the source files.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/daodaobing/codex-project-context/project-context
Any agent
npx skills add daodaobing/codex-project-context --skill project-context
Clone the repo
git clone --depth 1 https://github.com/daodaobing/codex-project-context

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,157 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00055 $0.01157
Opus 5 $0.00028 $0.00579
Sonnet 5 $0.00011 $0.00231
Haiku 4.5 $0.00006 $0.00116

Measured 2d ago against content hash 4291dd3493f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-context scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/project-context/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Context

Use the globally registered Context MCP Server to restore task-relevant project knowledge before coding. Keep the workflow lightweight: discover candidates first, read only what the task needs, then verify against source. Never replace AGENTS.md, docs, or Serena.

When to use this skill

Consider it when the task is likely to depend on project-specific knowledge:

  • unfamiliar project structure, or a repository you have not worked in yet;
  • architecture, configuration, or naming conventions that must be respected;
  • rules or design decisions spread across multiple docs;
  • a request that is too vague to locate the right code directly;
  • a change that should follow an existing design before editing.

Skip it and work directly when the task is self-contained:

  • the user gives an exact file path or function name;
  • a small, localized fix or a clear function-level bug;
  • the unique relevant file is already known;
  • a simple command or usage question;
  • a general task unrelated to this repository's documentation.

Two-stage workflow

Stage 1 — Candidate discovery

When project knowledge may be needed but it is unclear which documents matter, call get_context_candidates(project_path, task). It returns metadata only (path, title, summary, role, rank, reasons) for a small set of candidate documents. This call narrows the search space; it is not a full context load and not a document read.

Stage 2 — Selective reading

Read only the candidate documents the task actually needs, judged from the task plus each candidate's path, title, summary, role, and reasons. Reading one or two documents is normal; reading every candidate is not required. If the metadata already gives enough direction, continue straight to source verification.

Source and tests remain the final truth. Documents narrow the search and restore design context, but always confirm behavior against the current code.

Decision model

  1. Do I already have enough context? (exact file or function given, small change in known code) -> work directly.
  2. Does the task depend on project-specific knowledge rather than pure code logic? No -> work directly.
  3. Do I already know exactly which document or file to read? Yes -> read it directly.
  4. Otherwise -> get_context_candidates(project_path, task), read only the chosen candidates, then verify in source and tests.

Read the full file on GitHub · 87 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 87 lines · 55 tokens per session scan A 4291dd3493f9

Subscribe to this mod's changes

project-context is a skill published in the GitHub repository daodaobing/codex-project-context (1 stars, last pushed 16d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,157 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens